meeting-minutes-taker
Convert raw meeting transcripts into polished, structured meeting minutes.
Install
mkdir -p .claude/skills/meeting-minutes-taker && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2819" && unzip -o skill.zip -d .claude/skills/meeting-minutes-taker && rm skill.zipInstalls to .claude/skills/meeting-minutes-taker
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Transforms raw meeting transcripts into high-fidelity, structured meeting minutes (notes / summaries). Use when (1) a meeting transcript is provided and meeting minutes, notes, or a summary are requested; (2) multiple versions of minutes must be merged without losing content; (3) existing minutes need review against the original transcript for missing items; (4) the transcript has anonymous speakers like "Speaker 1/2/3" or "发言人1" that need identifying (optionally mapped via a context.md team directory). Triggers on 会议纪要 / 会议记录 / 整理纪要 / 妙记转纪要, "write meeting minutes", "summarize this meeting", "merge these minutes", "what's missing from these notes". For fixing ASR/STT recognition errors in the raw transcript first, use transcript-fixer; this skill structures clean transcripts into minutes.Key capabilities
- →Transform raw transcripts to structured minutes
- →Identify speakers via feature analysis
- →Merge multiple transcript versions
- →Generate Mermaid diagrams
- →Perform retrieval self-tests
How it works
It processes transcripts through parallel subagents to generate multiple versions, which are then merged and reviewed against the original text for completeness.
Inputs & outputs
When to use meeting-minutes-taker
- →Draft minutes from transcripts
- →Extract action items from meetings
- →Summarize group discussions
- →Formalize meeting outcomes
About this skill
Meeting Minutes Taker
Transform raw meeting transcripts into comprehensive, evidence-based meeting minutes through iterative review.
Quick Start
Pre-processing (Optional but Recommended):
- Document conversion: Use
doc-to-markdownskill to convert .docx/.pdf to Markdown first (preserves tables/images) - Transcript cleanup: Use
transcript-fixerskill to fix ASR/STT errors if transcript quality is poor - Context file: Prepare
context.mdwith team directory for accurate speaker identification
Core Workflow:
- Read the transcript and any supplied participant notes or user corrections using Step 1's source contract
- Load project-specific context file if provided by user (optional)
- Intelligent file naming: Auto-generate filename from content (see below)
- Speaker identification: If transcript has "Speaker 1/2/3", FIRST ask the user to label speakers on the source platform and re-export (see Step 1.5 Phase 0); infer from text only as a fallback
- Multi-turn generation: Use multiple passes or subagents with isolated context, merge using UNION
- Self-review using references/completeness_review_checklist.md
- Present draft to user for human line-by-line review
- Cross-AI comparison (optional): Human may provide output from other AI tools (e.g., Gemini, ChatGPT) - merge to reduce bias
- Iterate on feedback until human approves final version
Intelligent File Naming
Auto-generate output filename from transcript content:
Pattern: YYYY-MM-DD-<topic>-<type>.md
| Component | Source | Examples |
|---|---|---|
| Date | Transcript metadata or first date mention | 2026-01-25 |
| Topic | Main discussion subject (2-4 words, kebab-case) | api-design, product-roadmap |
| Type | Meeting category | review, sync, planning, retro, kickoff |
Examples:
2026-01-25-order-api-design-review.md2026-01-20-q1-sprint-planning.md2026-01-18-onboarding-flow-sync.md
Ask user to confirm the suggested filename before writing.
Core Workflow
Copy this checklist and track progress:
Meeting Minutes Progress:
- [ ] Step 0 (Optional): Pre-process transcript with transcript-fixer
- [ ] Step 1: Read and analyze transcript
- [ ] Step 1.5: Speaker identification (if transcript has "Speaker 1/2/3")
- [ ] Phase 0 FIRST: ask user to label speakers on the source platform (Feishu Minutes / Tencent Meeting), re-export, use labeled transcript
- [ ] Fallback only (source labeling unavailable or declined by user):
- [ ] Analyze speaker features (word count, style, topic focus)
- [ ] Match against context.md team directory (if provided)
- [ ] Present speaker mapping with per-speaker evidence to user for confirmation
- [ ] Step 1.6: Generate intelligent filename, confirm with user
- [ ] Step 1.7: Quality assessment (optional, affects processing depth)
- [ ] Step 2: Multi-turn generation (PARALLEL subagents with Task tool)
- [ ] Create transcript-specific dir: <output_dir>/intermediate/<transcript-name>/
- [ ] Launch 3 Task subagents IN PARALLEL (single message, 3 Task tool calls)
- [ ] Subagent 1 → <output_dir>/intermediate/<transcript-name>/version1.md
- [ ] Subagent 2 → <output_dir>/intermediate/<transcript-name>/version2.md
- [ ] Subagent 3 → <output_dir>/intermediate/<transcript-name>/version3.md
- [ ] Merge: UNION all versions, AGGRESSIVELY include ALL diagrams → draft_minutes.md
- [ ] Final: Compare draft against all supplied sources, reconcile final states, add omissions
- [ ] Step 3: Self-review for completeness
- [ ] Step 3.5: Retrieval Self-Test (consumption-side verification)
- [ ] Follow [Step 3.5](#step-35-retrieval-self-test-consumption-side-verification) and save its evidence
- [ ] Step 4: Present draft to user for human review
- [ ] Step 5: Cross-AI comparison (if human provides external AI output)
- [ ] Step 6: Iterate on human feedback (expect multiple rounds)
- [ ] Step 7: Human approves final version
Note: <output_dir> = directory where final meeting minutes will be saved (e.g., project-docs/meeting-minutes/)
Note: <transcript-name> = name derived from transcript file (e.g., 2026-01-15-product-api-design)
Step 1: Read and Analyze Transcript
Read all supplied sources before generation. Keep the transcript unchanged; record participant notes and user corrections separately with their author, date and source locator when known. Unknown metadata stays unknown. Give every generation pass the same source bundle. Notes need no separate reader-facing deliverable: integrate their substantive content into one current minutes document, link the transcript for verification, and retain original notes through the owning archive's source record. Follow an explicitly requested alternative delivery format.
Reconcile each fact within its stated scope. A later explicit participant correction or status update can revise that fact; it does not silently replace unrelated meeting decisions. If sources remain irreconcilable, state the conflict in Open Questions. Do not invent agreement. Significant transcript-backed decisions need original quotations with speaker attribution and timestamps. Record note-only additions under Source with the note's author/date or source label; do not fabricate a transcript quote, speaker or timestamp for them.
Bind each TODO/DONE to its exact action, owner, conditions and supporting source. Preserve unknown owners, deadlines and completion evidence as unknown. A note's author is not automatically the task owner. An invitation sent does not establish that the meeting occurred; finding an available account does not establish that someone switched accounts. Separate agreed responsibility from work delivered or a hypothesis verified.
Analyze the transcript to identify:
- Meeting topic and attendees
- Key decisions with supporting quotes
- Action items with owners
- Deferred items / open questions
Step 1.5: Speaker Identification (When Needed)
Trigger: Transcript only has generic labels like "Speaker 1", "Speaker 2", "发言人1", etc.
Phase 0: Source-Side Labeling (ALWAYS TRY FIRST)
When the transcript comes from a platform that supports manual speaker labeling (Feishu Minutes 飞书妙记, Tencent Meeting 腾讯会议, or any tool with a diarization-editing page), stop and ask the user to label the speakers at the source, then re-export/re-ingest the labeled transcript before generating minutes. Send the user the source page link — it is usually in the transcript's frontmatter (minute_url, meeting URL).
Why this beats inference:
- Platform labeling is a human listening to the actual voices — the authoritative source. Text-based inference can only resolve speakers who happen to get name-called during the meeting; everyone else stays a guess.
- Diarization-merged segments (multiple people collapsed into one label) are unrecoverable from text alone — no amount of inference fixes them, but source-side relabeling does.
- Inference output forces
[inferred]markers everywhere plus a per-speaker human review round; source labeling produces clean ground truth once.
Fall back to Phase A–C below only when: (a) the user explicitly says to proceed by inference, or (b) the source cannot be labeled (raw audio file with no platform page, no edit permission). In the fallback, every mapping must carry evidence and a confidence level, unresolved labels stay as-is (never force-assign), and when the user later labels the source, go back and correct the minutes.
Fallback approach (inspired by Anker Skill):
Phase A: Feature Analysis (Pattern Recognition)
For each speaker, analyze:
| Feature | What to Look For |
|---|---|
| Word count | Total words spoken (high = senior/lead, low = observer) |
| Segment count | Number of times they speak (frequent = active participant) |
| Avg segment length | Average words per turn (long = presenter, short = responder) |
| Filler ratio | % of filler words (对/嗯/啊/就是/然后) - low = prepared speaker |
| Speaking style | Formal/informal, technical depth, decision authority |
| Topic focus | Areas they discuss most (backend, frontend, product, etc.) |
| Interaction pattern | Do others ask them questions? Do they assign tasks? |
Example analysis output:
Speaker Analysis:
┌──────────┬────────┬──────────┬─────────────┬─────────────┬────────────────────────┐
│ Speaker │ Words │ Segments │ Avg Length │ Filler % │ Role Guess │
├──────────┼────────┼──────────┼─────────────┼─────────────┼────────────────────────┤
│ 发言人1 │ 41,736 │ 93 │ 449 chars │ 3.6% │ 主讲人 (99% of content)│
│ 发言人2 │ 101 │ 8 │ 13 chars │ 4.0% │ 对话者 (short responses)│
└──────────┴────────┴──────────┴─────────────┴─────────────┴────────────────────────┘
Inference rules:
- 占比 > 70% + 平均长度 > 100字 → 主讲人
- 平均长度 < 50字 → 对话者/响应者
- 语气词占比 < 5% → 正式/准备充分
- 语气词占比 > 10% → 非正式/即兴发言
Phase B: Context Mapping (If Context File Provided)
When user provides a project context file (e.g., context.md):
- Load team directory section
- Match feature patterns to known team members
- Cross-reference roles with speaking patterns
Context file should include:
## Team Directory
| Name | Role | Communication Style |
|------|------|---------------------|
| Alice | Backend Lead | Technical, decisive, assigns backend tasks |
| Bob | PM | Product-focused, asks requirements questions |
| Carol | TPM | Process-focused, tracks timeline/resources |
Phase C: Confirmation Before Proceeding
CRITICAL: Never silently assume speaker identity.
Present analysis summary to user:
Speaker Analysis:
- Speaker 1 → Alice (Backend Lead) - 80% confidence based on: technical focus, task assignment pattern
- Speaker 2 → Bob (PM) - 75% confidence based on: product questions, requirements discussion
- Speaker 3 → Ca
---
*Content truncated.*
When not to use it
- →When the transcript is not provided
- →When the user refuses to label speakers at the source
Prerequisites
Limitations
- →Requires human review for final approval
- →Inferred speaker identification is less accurate than source-side labeling
How it compares
It uses multi-turn parallel generation and iterative self-testing rather than simple summarization.
Compared to similar skills
meeting-minutes-taker side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| meeting-minutes-taker (this skill) | 1 | 4mo | Review | Intermediate |
| executive-briefing | 5 | 11mo | No flags | Beginner |
| video-report | 7 | 6mo | No flags | Beginner |
| ks | 0 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by daymade
View all by daymade →You might also like
executive-briefing
anthropics
Transforms research findings into executive-ready briefings. Automatically activated when user mentions 'executive', 'briefing', 'C-suite', 'board', 'leadership', or 'presentation'.
video-report
remotion-dev
Generate a report about a video
ks
DoIT-Artificial-Intelligence
(Kitchen Sink) Process a YouTube video with all features (summary, Q&A, infographic, audio, and video).
ExtractWisdom
jjchambers80
Content-adaptive wisdom extraction — detects what domains exist in content and builds custom sections (not static IDEAS/QUOTES). Produces tailored insight reports from videos, podcasts, articles. USE WHEN extract wisdom, analyze video, analyze podcast, extract insights, what's interesting, extract f
rfp_contents
yellowCornSalad
공고 카드의 콘텐츠 품질 점검 + LLM 자동 요약. 예산·기간 정확성, 본문 가독성, 키워드 매칭 정확성, 상세보기 가독성 5축 점검 + 카드에 본문+첨부 종합 150자 요약을 ai_summary 컬럼에 저장.
yt
ZeroPointRepo
Use when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content — even if YouTube is not mentioned explicitly. Covers transcripts, search, and channel latest. Not for uploads or account